Variables & Loops

# Setting variables — no spaces around =
SAMPLE="SRR123456"
GENOME="/data/references/GRCh38.fa"
THREADS=8
OUTDIR="~/bash-linux-bioinformatics/results"

# Using variables with $
echo "Sample ID: $SAMPLE"
Sample ID: SRR123456

echo "Using genome: $GENOME"
Using genome: /data/references/GRCh38.fa

# Use ${} when the variable is followed immediately by more text
echo "Output file: ${SAMPLE}_aligned.bam"
Output file: SRR123456_aligned.bam

# THIS FAILS — Bash looks for variable named SAMPLE_aligned, not SAMPLE
echo "$SAMPLE_aligned.bam"
.bam   # wrong! Variable not found, so empty string

NAME="Shajedur"

echo "Hello $NAME"     # double quotes — variable IS expanded
Hello Shajedur

echo 'Hello $NAME'     # single quotes — variable is NOT expanded
Hello $NAME

# $? — exit status of the last command
ls species.txt
echo "Exit status: $?"
Exit status: 0           # 0 = success

ls nonexistent.txt
echo "Exit status: $?"
Exit status: 2           # non-zero = failure

# $$ — current process ID (useful for unique temp files)
echo "My PID is: $$"
My PID is: 12345         # number varies every time

# Creating a unique temp file using $$
TMPFILE="/tmp/bioinfo_temp_$$.txt"
echo "Temp file: $TMPFILE"
Temp file: /tmp/bioinfo_temp_12345.txt

# Basic arithmetic with $(( ))
echo $((2 + 2))
4

echo $((10 - 3))
7

echo $((6 * 7))
42

echo $((17 / 4))
4                  # integer division only — remainder is dropped

echo $((17 % 4))
1                  # % = modulo (remainder)

# Store result in a variable
LINES=$(wc -l < sample.fastq)
READS=$(( LINES / 4 ))
echo "Lines: $LINES | Reads: $READS"
Lines: 12 | Reads: 3

# Increment a counter (add 1)
COUNT=0
COUNT=$(( COUNT + 1 ))
echo "$COUNT"
1

# Capture command output into a variable
TODAY=$(date +%Y-%m-%d)
echo "Today is: $TODAY"
Today is: 2026-06-17

FILE_COUNT=$(ls ~/bash-linux-bioinformatics/module-1-foundations/ | wc -l)
echo "Files in folder: $FILE_COUNT"

# Capture wc output cleanly (< sends file as stdin, avoids filename in output)
LINES=$(wc -l < sample.fastq)
echo "Line count: $LINES"

# Define an array of sample names
SAMPLES=("SRR001" "SRR002" "SRR003" "SRR004")

# Access individual items — index starts at 0
echo "${SAMPLES[0]}"
SRR001

echo "${SAMPLES[2]}"
SRR003

# Access all items
echo "${SAMPLES[@]}"
SRR001 SRR002 SRR003 SRR004

# Count items in the array
echo "Number of samples: ${#SAMPLES[@]}"
Number of samples: 4

# Array of chromosome names — real bioinformatics use case
CHROMOSOMES=("chr1" "chr2" "chr3" "chrX" "chrY")
echo "Processing ${#CHROMOSOMES[@]} chromosomes"
Processing 5 chromosomes

# Basic for loop — iterate over a list of values
for SPECIES in maize rice sorghum wheat; do
    echo "Processing: $SPECIES"
done
Processing: maize
Processing: rice
Processing: sorghum
Processing: wheat

# Loop over an array of sample names
SAMPLES=("SRR001" "SRR002" "SRR003")
for SAMPLE in "${SAMPLES[@]}"; do
    echo "Running FastQC on: ${SAMPLE}.fastq"
done
Running FastQC on: SRR001.fastq
Running FastQC on: SRR002.fastq
Running FastQC on: SRR003.fastq

# Loop over a numeric range with {start..end}
for I in {1..5}; do
    echo "Iteration $I"
done
Iteration 1
Iteration 2
Iteration 3
Iteration 4
Iteration 5

# Loop over all .txt files in a folder
for FILE in ~/bash-linux-bioinformatics/module-1-foundations/*.txt; do
    echo "Found: $FILE"
    wc -l "$FILE"
done

# Basic while loop — count from 1 to 3
COUNT=1
while [ $COUNT -le 3 ]; do
    echo "Count: $COUNT"
    COUNT=$(( COUNT + 1 ))
done
Count: 1
Count: 2
Count: 3

# Read a file line by line — essential for sample sheets
while read LINE; do
    echo "Processing sample: $LINE"
done < species.txt
Processing sample: Sorghum bicolor
Processing sample: Arabidopsis thaliana
Processing sample: Oryza sativa

# Read multiple columns from a tab-separated file
# Imagine sample_sheet.txt has: SAMPLE_ID  FASTQ_PATH  CONDITION
while read SAMPLE FASTQ CONDITION; do
    echo "Sample: $SAMPLE | File: $FASTQ | Group: $CONDITION"
done < sample_sheet.txt

# Create a tab-separated sample sheet (use $'\t' for a real tab character)
printf "control_1\tdata/raw/control_1.fastq\tcontrol\n" >  sample_sheet.txt
printf "control_2\tdata/raw/control_2.fastq\tcontrol\n" >> sample_sheet.txt
printf "treated_1\tdata/raw/treated_1.fastq\tcontreated\n" >> sample_sheet.txt
printf "treated_2\tdata/raw/treated_2.fastq\ttreated\n"  >> sample_sheet.txt

# Now run the while read loop
while read SAMPLE FASTQ CONDITION; do
    echo "Sample: $SAMPLE | File: $FASTQ | Group: $CONDITION"
done < sample_sheet.txt
Sample: control_1 | File: data/raw/control_1.fastq | Group: control
Sample: control_2 | File: data/raw/control_2.fastq | Group: control
Sample: treated_1 | File: data/raw/treated_1.fastq | Group: treated
Sample: treated_2 | File: data/raw/treated_2.fastq | Group: treated

# ── Pattern 1: Run a tool on every FASTQ file in a folder ──
for FASTQ in ~/data/raw/*.fastq.gz; do
    SAMPLE=$(basename "$FASTQ" .fastq.gz)   # strip folder path and extension
    echo "Running FastQC on: $SAMPLE"
    # fastqc "$FASTQ" --outdir ~/results/fastqc/  (real command when FastQC installed)
done

# ── Pattern 2: Create output folders for each sample ──
SAMPLES=("control_1" "control_2" "treated_1" "treated_2")
for SAMPLE in "${SAMPLES[@]}"; do
    mkdir -p "~/bash-linux-bioinformatics/results/${SAMPLE}"
    echo "Created folder for: $SAMPLE"
done

# ── Pattern 3: Count reads in every FASTQ file ──
for FILE in ~/bash-linux-bioinformatics/module-1-foundations/*.fastq; do
    LINES=$(wc -l < "$FILE")
    READS=$(( LINES / 4 ))
    NAME=$(basename "$FILE")
    echo "$NAME: $READS reads"
done

# ── Pattern 4: Add a prefix to every filename ──
for FILE in ~/bash-linux-bioinformatics/module-1-foundations/*.txt; do
    BASENAME=$(basename "$FILE")
    DIR=$(dirname "$FILE")
    mv "$FILE" "${DIR}/backup_${BASENAME}"
    echo "Renamed: $BASENAME → backup_$BASENAME"
done

# basename — get just the filename
basename "/home/shajedur/data/SRR001.fastq.gz"
SRR001.fastq.gz

# basename — strip extension too
basename "/home/shajedur/data/SRR001.fastq.gz" ".fastq.gz"
SRR001

# dirname — get just the folder path
dirname "/home/shajedur/data/SRR001.fastq.gz"
/home/shajedur/data